Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2045 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.5292. Min Act: -0.1700
Data Index: 982574 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4980. Min Act: -0.1700
Data Index: 914311 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.5292. Min Act: -0.1700
Data Index: 695085 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4667. Min Act: -0.1700
Data Index: 174476 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4355. Min Act: -0.1700
Data Index: 843107 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4355. Min Act: -0.1700
Data Index: 927877 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4355. Min Act: -0.1700
Data Index: 245317 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4355. Min Act: -0.1700
Data Index: 1213981 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4355. Min Act: -0.1700
Data Index: 452457 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4667. Min Act: -0.1700
Data Index: 1035920 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 566622 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 1048026 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4667. Min Act: -0.1700
Data Index: 584371 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4355. Min Act: -0.1700
Data Index: 1154459 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 261735 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.3730. Min Act: -0.1700
Data Index: 946353 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 155466 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.3105. Min Act: -0.1700
Data Index: 835885 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.4042. Min Act: -0.1700
Data Index: 442267 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5292. Min Range: -4.5292
Max Act: 4.3730. Min Act: -0.1700
Data Index: 227762 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19